From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-wi0-f179.google.com (mail-wi0-f179.google.com [209.85.212.179]) by dpdk.org (Postfix) with ESMTP id 7587958EE for ; Mon, 3 Nov 2014 23:20:32 +0100 (CET) Received: by mail-wi0-f179.google.com with SMTP id h11so7743398wiw.6 for ; Mon, 03 Nov 2014 14:29:48 -0800 (PST) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:from:to:cc:subject:date:message-id:organization :user-agent:in-reply-to:references:mime-version :content-transfer-encoding:content-type; bh=Bz/g7q3b+OaKorEK1C2BeeQ2lkLg2JU2O0+kp2+6w2U=; b=JfFxmnfqh9Yc+d4GWkLjViIp28DrxUIKaQKONAj/arVJJgyWvCLHZXus0uwWmlOYnl IPOlVJnThaImR4RN2o9dFlOHBiVDzvXYUcCmkVLeh24TrELvBZL8RdQKowWoIb+wx5Z0 qECj3TAO3n5kgNWK8xlSOK7UskqguRA8wbNSWANTjsFV+JEplW/PpOnkoq4hshcli7qI L3Loj65MyjtHOIVylLYEetXc4RkJGX4kUhnQ6agnhfUsZtIkWiv2xfNBg2RQn6z7K7SG d592D8UURkbesQBBuJ/DcvKirYc2cZ63PKwSxl/fG+KiRW0kg8M7b89CDkGGTTxRPgEx dPLg== X-Gm-Message-State: ALoCoQlVTl5o43Kqx+BnMX2nuZs8gHkfHaIJMkQ7m2tQTmBVkBHai/AdyAGLuuyPHmzCjY+AQ7mU X-Received: by 10.180.182.195 with SMTP id eg3mr19607314wic.31.1415053788187; Mon, 03 Nov 2014 14:29:48 -0800 (PST) Received: from xps13.localnet (guy78-1-82-235-116-147.fbx.proxad.net. [82.235.116.147]) by mx.google.com with ESMTPSA id fm10sm10183262wib.21.2014.11.03.14.29.46 for (version=TLSv1.2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Mon, 03 Nov 2014 14:29:47 -0800 (PST) From: Thomas Monjalon To: Aaron Campbell Date: Mon, 03 Nov 2014 23:29:29 +0100 Message-ID: <1466122.G25iygG7Yz@xps13> Organization: 6WIND User-Agent: KMail/4.14.2 (Linux/3.17.1-1-ARCH; KDE/4.14.2; x86_64; ; ) In-Reply-To: References: <1404808110-16314-1-git-send-email-simon.kuenzer@neclab.eu> <53CFA637.1090706@neclab.eu> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" Cc: dev@dpdk.org Subject: Re: [dpdk-dev] [PATCH] eal/linuxapp: Add parameter to specify master lcore id X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 03 Nov 2014 22:20:32 -0000 2014-11-03 13:02, Aaron Campbell: > Hi Simon, >=20 > Thanks for the patch, this will be useful for us. I responded separa= tely to your original post with one suggestion. >=20 > Our application currently assumes that DPDK will assign the first bit= set in the coremask to the master lcore. As far as I can tell, this i= s hard-coded as of 1.7.1. But we would like the ability for our applic= ation to specify any bit from the coremask to serve as the master lcore= . >=20 > I don=E2=80=99t see any compatibility issues with this. Existing app= lications should behave as before. >=20 > Thomas, could this be accepted for the 1.8 release? Or will that onl= y happen if the BSD side can be patched as well? No need for BSD side patch because option management is now common betw= een BSD and Linux. I'm going to send an updated version of this patch. > > On Jul 23, 2014, at 9:10 AM, Simon Kuenzer wrote: > >=20 > > Hi all, > >=20 > > the only issue I could imagine is that current DPDK applications ar= e > > utilizing the implicit assumption that the master lcore is always s= et to > > the first available lcore. I would consider this as a "bug" in the > > application because it sets up its worker threads not "properly". > >=20 > > However, as far I could check it, the DPDK framework seems to cope = with > > it correctly. > > It would be nice if somebody else could confirm my statement. > >=20 > > Thanks, > >=20 > > Simon > >=20 > > On 23.07.2014 10:53, Hiroshi Shimamoto wrote: > >> Hi, > >>=20 > >>> Subject: Re: [dpdk-dev] [PATCH] eal/linuxapp: Add parameter to sp= ecify master lcore id > >>>=20 > >>> Hi Hiroshi, > >>>=20 > >>> 2014-07-22 23:40, Hiroshi Shimamoto: > >>>> does anyone have interest in this functionality? > >>>>=20 > >>>> I think this is important and useful. > >>>> Since we should care about core assignment to get high performan= ce > >>>> and the master lcore thread is special in DPDK, we will want to > >>>> assign the master to the target core. > >>>> For example, with hyperthreading I'd like to make a pair of pack= et > >>>> processing threads into one physical core and separate the maste= r > >>>> thread which does some management. > >>>=20 > >>> Thank you for showing your interest. > >>> Does it mean you carefully reviewed this patch? In this case, I'd= appreciate > >>> a note "Reviewed-by:". > >>=20 > >> Not yet deeply, wait a bit, we're testing this patch in our applic= ation. > >> Will report if it works fine. > >>=20 > >> By the way, we should add the same code into the BSD code, right? > >>=20 > >> thanks, > >> Hiroshi